System, method and computer program for improved forecasting residual values of a durable good over time

• US 10,430,814 B2
• Filed: 10/11/2017
• Issued: 10/01/2019
• Est. Priority Date: 08/15/2012
• Status: Active Grant

• Current Assignee: J.D. Power
• Original Assignee: ALG, Inc. (TrueCar, Inc.)
• Inventors: Hansen, Morgan Scott, Abe, Brian Izumi, Strauss, Oliver Thomas Sidney
• Primary Examiner(s): Miller, Alan S
• Application Number:
  US15/729,719
• Publication Number:
  US 20180033030A1
• Time in Patent Office: 720 Days
• Field of Search: 705 711- 742
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 10/30 Administration of product recycling or disposal
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0205 Location or geographical consideration
• CPC Class Codes: G06Q 30/0206 Price or cost determination based on market factors
• CPC Class Codes: Y02W 90/00 Enabling technologies or technologies with a potential or indirect contribution to greenhouse gas [GHG] emissions mitigation

Abstract

A residual value forecasting system may utilize heterogeneous data, such as used market data, industry-specific data, and non-industry-specific data, from disparate data sources to produce residual value forecasts of an item based on a sophisticated residual value forecasting model particularly configured for agility. The system can dynamically and quickly adapt to change in data inputs and produce custom outputs. The system may determine a baseline value for an item using the used market data, a microeconomic factor using the industry-specific data, and a macroeconomic factor using the non-industry-specific data, as well as adjustments such as locality adjustments and modifications. Given the macroeconomic factor and the microeconomic factor relative to the locality-adjusted value of the item and in view of the competitive sets of similar and/or substitute items in the same industry, the system can generate an accurate forecast residual value of the item at a future time point.

Claims

1. A method, comprising:

collecting used market data, non-industry-specific data, and industry-specific data from disparate data sources into a database, the collecting performed simultaneously, continuously, or periodically by a system communicatively connected to the disparate data sources over a network, the system having a processor and a non-transitory computer-readable medium;

transforming, by the system, all or part of the used market data, the non-industry-specific data, and the industry-specific data into data representations internal to the system;

determining, by the system using the used market data, a baseline value for an item of interest with a base configuration in an industry at an initial time point, the determining comprising taking an average of historical market values from the used market data;

determining, by the system at the initial time point, a reference period at which the baseline value for the item of interest is adjusted;

determining, by the system, a number of forecasts desired between the initial time point and the reference period;

determining, by the system, a locality adjustment to the item of interest at a forecast time, the locality adjustment representing a ratio of an average cost of items in the industry in a locality at the forecast time over a local cost of items in the industry across all localities at the forecast time;

determining, by the system, a locality-adjusted value of the item of interest as modified at the forecast time;

constructing, by the system, competitive sets of similar items, substitute items, or a combination thereof in the industry to which the item of interest belongs;

determining, by the system, to which one and only one of the competitive sets the item of interest belongs;

determining, by the system using the non-industry-specific data, a macroeconomic factor by taking a set of macroeconomic variables over a plurality of industries, the set of macroeconomic variables representing macroeconomic features;

determining, by the system using the industry-specific data, a microeconomic factor by taking a linear combination of observed or forecasted values of microeconomic variables specific to the industry to which the item of interest belongs;

generating, by the system at the forecast time, a residual value for the item of interest, the generating utilizing the baseline value for the item of interest at the initial time point determined by the system using the used market data, the macroeconomic factor determined by the system using the non-industry-specific data, and the microeconomic factor determined by the system using the industry-specific data;

storing the residual value for the item of interest in a data storage device; and

providing the residual value forecast for the item of interest for presentation on a client device over the network.

2. The method according to claim 1, wherein the system determines the baseline value for the item of interest responsive to a request from a client device communicatively connected to the system over a network, responsive to an instruction or command from an administrator of the system through a user interface of the system, or responsive to a programmed trigger or scheduled event.

3. The method according to claim 1, further comprising:

constructing competitive sets of similar items in the industry of the item of interest, substitute items in the industry of the item of interest, or a combination thereof;

selecting a most similar item from the competitive sets, the substitute items, or the combination thereof as a substitute for the item of interest in the industry; and

using a baseline value for the substitute as the baseline value for the item of interest in subsequent steps if the baseline value for the item of interest cannot be determined or obtained from the historical market values.

4. The method according to claim 1, wherein the system determines the reference period based at least in part on a minimum frequency in which input data from the disparate data sources to the system is updated, an expected total lifetime of the item of interest, or a utility of the residual value forecast generated by the system for the item of interest.

5. The method according to claim 1, wherein the locality adjustment comprises a first modification type and a second modification type, wherein the first modification type represents any modifications made to the base configuration of the item of interest at a time point in the reference period that are observable and are expected to retain some value in future time periods after the reference period, and wherein the second modification type represents any modifications made to the base configuration of the item of interest at the time point in the reference period that are not observable, not expected to retain value, or both.

6. The method according to claim 1, wherein the used market data comprises open auction data, closed auction data, and certified pre-owned data.

7. The method according to claim 1, wherein the macroeconomic features comprise gas prices, an economic index, and industry supply, and wherein the microeconomic variables comprise segment supply, model supply, incentive spending, fleet management, redesign, and brand value.

8. A system, comprising:

a processor;

a non-transitory computer-readable medium; and

stored instructions translatable by the processor to perform;

collecting used market data, non-industry-specific data, and industry-specific data from disparate data sources into a database simultaneously, continuously, or periodically over a network;

transforming all or part of the used market data, the non-industry-specific data, and the industry-specific data into data representations internal to the system;

determining, using the used market data, a baseline value for an item of interest with a base configuration in an industry at an initial time point, the determining comprising taking an average of historical market values from the used market data;

determining, at the initial time point, a reference period at which the baseline value for the item of interest is adjusted;

determining a number of forecasts desired between the initial time point and the reference period;

determining a locality adjustment to the item of interest at a forecast time, the locality adjustment representing a ratio of an average cost of items in the industry in a locality at the forecast time over a local cost of items in the industry across all localities at the forecast time;

determining a locality-adjusted value of the item of interest as modified at the forecast time;

constructing competitive sets of similar items, substitute items, or a combination thereof in the industry to which the item of interest belongs;

determining to which one and only one of the competitive sets the item of interest belongs;

determining, using the non-industry-specific data, a macroeconomic factor by taking a set of macroeconomic variables over a plurality of industries, the set of macroeconomic variables representing macroeconomic features;

determining, using the industry-specific data, a microeconomic factor by taking a linear combination of observed or forecasted values of microeconomic variables specific to the industry to which the item of interest belongs;

generating, at the forecast time, a residual value for the item of interest, the generating utilizing the baseline value for the item of interest at the initial time point determined by the system using the used market data, the macroeconomic factor determined by the system using the non-industry-specific data, and the microeconomic factor determined by the system using the industry-specific data;

storing the residual value for the item of interest in a data storage device; and

providing the residual value forecast for the item of interest for presentation on a client device over the network.

9. The system of claim 8, wherein the system determines the baseline value for the item of interest responsive to a request from a client device communicatively connected to the system over a network, responsive to an instruction or command from an administrator of the system through a user interface of the system, or responsive to a programmed trigger or scheduled event.

10. The system of claim 9, wherein the instructions are further translatable by the processor to perform:

constructing competitive sets of similar items in the industry of the item of interest, substitute items in the industry of the item of interest, or a combination thereof;

selecting a most similar item from the competitive sets, the substitute items, or the combination thereof as a substitute for the item of interest in the industry; and

using a baseline value for the substitute as the baseline value for the item of interest in subsequent steps if the baseline value for the item of interest cannot be determined or obtained from the historical market values.

11. The system of claim 8, wherein the system determines the reference period based at least in part on a minimum frequency in which input data from the disparate data sources to the system is updated, an expected total lifetime of the item of interest, or a utility of the residual value forecast generated by the system for the item of interest.

12. The system of claim 8, wherein the locality adjustment comprises a first modification type and a second modification type, wherein the first modification type represents any modifications made to the base configuration of the item of interest at a time point in the reference period that are observable and are expected to retain some value in future time periods after the reference period, and wherein the second modification type represents any modifications made to the base configuration of the item of interest at the time point in the reference period that are not observable, not expected to retain value, or both.

13. The system of claim 8, wherein the used market data comprises open auction data, closed auction data, and certified pre-owned data.

14. The system of claim 8, wherein the macroeconomic features comprise gas prices, an economic index, and industry supply, and wherein the microeconomic variables comprise segment supply, model supply, incentive spending, fleet management, redesign, and brand value.

15. A computer program product comprising a non-transitory computer-readable medium storing instructions translatable by a processor of a residual value forecasting system for:

collecting used market data, non-industry-specific data, and industry-specific data from disparate data sources into a database simultaneously, continuously, or periodically over a network;

transforming all or part of the used market data, the non-industry-specific data, and the industry-specific data into data representations internal to the residual value forecasting system;

determining, using the used market data, a baseline value for an item of interest with a base configuration in an industry at an initial time point, the determining comprising taking an average of historical market values from the used market data;

determining, at the initial time point, a reference period at which the baseline value for the item of interest is adjusted;

determining a number of forecasts desired between the initial time point and the reference period;

determining a locality adjustment to the item of interest at a forecast time, the locality adjustment representing a ratio of an average cost of items in the industry in a locality at the forecast time over a local cost of items in the industry across all localities at the forecast time;

determining a locality-adjusted value of the item of interest as modified at the forecast time;

constructing competitive sets of similar items, substitute items, or a combination thereof in the industry to which the item of interest belongs;

determining to which one and only one of the competitive sets the item of interest belongs;

determining, using the non-industry-specific data, a macroeconomic factor by taking a set of macroeconomic variables over a plurality of industries, the set of macroeconomic variables representing macroeconomic features;

determining, using the industry-specific data, a microeconomic factor by taking a linear combination of observed or forecasted values of microeconomic variables specific to the industry to which the item of interest belongs;

generating, at the forecast time, a residual value for the item of interest, the generating utilizing the baseline value for the item of interest at the initial time point determined using the used market data, the macroeconomic factor determined using the non-industry-specific data, and the microeconomic factor determined using the industry-specific data;

storing the residual value for the item of interest in a data storage device; and

providing the residual value forecast for the item of interest for presentation on a client device over the network.

16. The computer program product of claim 15, wherein the baseline value for the item of interest is determined responsive to a request from a client device communicatively connected to the system over a network, responsive to an instruction or command from an administrator of the residual value forecasting system through a user interface of the residual value forecasting system, or responsive to a programmed trigger or scheduled event.

17. The computer program product of claim 15, wherein the instructions are further translatable by the processor for:

constructing competitive sets of similar items in the industry of the item of interest, substitute items in the industry of the item of interest, or a combination thereof;

selecting a most similar item from the competitive sets, the substitute items, or the combination thereof as a substitute for the item of interest in the industry; and

using a baseline value for the substitute as the baseline value for the item of interest in subsequent steps if the baseline value for the item of interest cannot be determined or obtained from the historical market values.

18. The computer program product of claim 15, wherein the reference period is determined based at least in part on a minimum frequency in which input data from the disparate data sources is updated, an expected total lifetime of the item of interest, or a utility of the residual value forecast generated for the item of interest.

19. The computer program product of claim 15, wherein the locality adjustment comprises a first modification type and a second modification type, wherein the first modification type represents any modifications made to the base configuration of the item of interest at a time point in the reference period that are observable and are expected to retain some value in future time periods after the reference period, and wherein the second modification type represents any modifications made to the base configuration of the item of interest at the time point in the reference period that are not observable, not expected to retain value, or both.

20. The computer program product of claim 15, wherein the used market data comprises open auction data, closed auction data, and certified pre-owned data.